jobautomation/
OpenEuroLLM-Slovenian:latest

104 6 months ago

🇪🇺 Perfect for Slovenian-speaking users who need AI assistance with information, creative writing, or conversation in their native language. We support European linguistic diversity.

vision

6 months ago

99fb765a51d0 · 8.1GB ·

model
gemma3
·
12.2B
·
Q4_K_M
license
Gemma Terms of Use Last modified: February 21, 2024 By using, reproducing, modifying, distributing,
system
Vedno boš odgovarjal v pravilni in naravni slovenščini. Si koristen in prijazen pomočnik, ki pom
license
CC BY-NC-SA 4.0
params
{ "num_ctx": 2048, "num_gpu": 1, "repeat_penalty": 1.1, "stop": [ "User:",
template
{{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 }} {{- if or (eq .Rol

Readme

OpenEuroLLM-Slovenian

A fine-tuned version of Gemma3 optimized for Slovenian language responses. This model is part of the JobAutomation Collection, aimed at providing high-quality language models for European languages.

Overview

OpenEuroLLM-Slovenian is specifically designed to provide fluent, natural responses in Slovenian. The model maintains the reasoning capabilities of its Gemma3 base while being optimized to understand and generate authentic Slovenian text.

Features

  • Native Slovenian Responses: Always responds in natural, correct Slovenian
  • Culturally Aware: Understanding of Slovenian culture, history, and regional context
  • Specialized Vocabulary: Prioritizes genuine Slovenian vocabulary over loan words
  • Grammatical Accuracy: Properly handles Slovenian-specific grammar rules and constructions
  • Fast & Efficient: Based on the efficient Gemma3 architecture for good performance even on consumer hardware

Usage

# Pull the model
ollama pull jobautomation/OpenEuroLLM-Slovenian

# Run the model
ollama run jobautomation/OpenEuroLLM-Slovenian

Model Details

  • Base Model: Gemma3
  • Context Length: 8K tokens
  • Training: Fine-tuned on a diverse corpus of Slovenian text including literature, news, academic papers, and conversational data
  • License: Apache 2.0
  • Recommended RAM: 8GB minimum

System Prompt

This model uses the following default system prompt:

Vedno boš odgovarjal v pravilni in naravni slovenščini. Si koristen in prijazen pomočnik, ki pomaga uporabnikom pri njihovih vprašanjih v slovenščini. Raje uporabljaš pristno slovensko besedišče in se izogibaš tujkam.

Customization

You can create a custom version with different parameters:

# Create a Modelfile
echo 'FROM jobautomation/OpenEuroLLM-Slovenian
PARAMETER temperature 0.7
PARAMETER top_p 0.9
SYSTEM "Vedno boš odgovarjal v pravilni in naravni slovenščini."' > Modelfile

# Create your custom model
ollama create slovak-academic -f Modelfile

About OpenEuroLLM

OpenEuroLLM is an initiative to create high-quality language models for European languages. Our mission is to ensure that AI language technologies support the linguistic diversity of Europe, providing models that understand and generate content in languages beyond the dominant few.

Acknowledgements

This model was developed with support of the open source community and Ollama.